© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45732
    Prev
    Next
    INDEX
    Explanations

    which is better

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    琥
    0.40
     शरद
    0.40
    ברו
    0.38
     himself
    0.37
    frequencies
    0.37
    神奇
    0.37
     usually
    0.36
    மைகள்
    0.36
    скоп
    0.36
    medio
    0.35
    POSITIVE LOGITS
    娉
    0.49
     बड़
    0.49
     felhasznál
    0.46
    গ্রহায়ণ
    0.44
     kullanıcı
    0.44
     stumpage
    0.43
    মেয়
    0.42
    цыяна
    0.42
     detract
    0.41
     విని
    0.40
    Activations Density 0.005%

    No Known Activations